© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74972
    Prev
    Next
    INDEX
    Explanations

    search query or location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    踅
    -1.59
    这不是
    -1.51
    是個
    -1.50
    嗵
    -1.48
    不夠
    -1.47
    有著
    -1.47
    chuckles
    -1.34
    請繼續
    -1.33
    
    -1.32
    licopter
    -1.30
    POSITIVE LOGITS
    0
    1.48
    casila
    1.48
     Cuando
    1.42
     Karl
    1.39
     ferner
    1.38
    -
    1.37
    section
    1.35
    </em>
    1.35
     nightclub
    1.32
     们
    1.29
    Activations Density 0.020%

    No Known Activations